From: Yonghong Song <yhs@fb.com>
To: Andrii Nakryiko <andriin@fb.com>, <bpf@vger.kernel.org>,
Martin KaFai Lau <kafai@fb.com>, <netdev@vger.kernel.org>
Cc: Alexei Starovoitov <ast@fb.com>,
Daniel Borkmann <daniel@iogearbox.net>, <kernel-team@fb.com>
Subject: [PATCH bpf-next v1 07/19] bpf: create anonymous bpf iterator
Date: Mon, 27 Apr 2020 13:12:42 -0700 [thread overview]
Message-ID: <20200427201242.2995160-1-yhs@fb.com> (raw)
In-Reply-To: <20200427201235.2994549-1-yhs@fb.com>
A new bpf command BPF_ITER_CREATE is added.
The anonymous bpf iterator is seq_file based.
The seq_file private data are referenced by targets.
The bpf_iter infrastructure allocated additional space
at seq_file->private after the space used by targets
to store some meta data, e.g.,
prog: prog to run
session_id: an unique id for each opened seq_file
seq_num: how many times bpf programs are queried in this session
has_last: indicate whether or not bpf_prog has been called after
all valid objects have been processed
A map between file and prog/link is established to help
fops->release(). When fops->release() is called, just based on
inode and file, bpf program cannot be located since target
seq_priv_size not available. This map helps retrieve the prog
whose reference count needs to be decremented.
Signed-off-by: Yonghong Song <yhs@fb.com>
---
include/linux/bpf.h | 3 +
include/uapi/linux/bpf.h | 6 ++
kernel/bpf/bpf_iter.c | 162 ++++++++++++++++++++++++++++++++-
kernel/bpf/syscall.c | 27 ++++++
tools/include/uapi/linux/bpf.h | 6 ++
5 files changed, 203 insertions(+), 1 deletion(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4fc39d9b5cd0..0f0cafc65a04 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1112,6 +1112,8 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd);
int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
int bpf_obj_get_user(const char __user *pathname, int flags);
+#define BPF_DUMP_SEQ_NET_PRIVATE BIT(0)
+
struct bpf_iter_reg {
const char *target;
const char *target_func_name;
@@ -1133,6 +1135,7 @@ int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx);
int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
int bpf_iter_link_replace(struct bpf_link *link, struct bpf_prog *old_prog,
struct bpf_prog *new_prog);
+int bpf_iter_new_fd(struct bpf_link *link);
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f39b9fec37ab..576651110d16 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -113,6 +113,7 @@ enum bpf_cmd {
BPF_MAP_DELETE_BATCH,
BPF_LINK_CREATE,
BPF_LINK_UPDATE,
+ BPF_ITER_CREATE,
};
enum bpf_map_type {
@@ -590,6 +591,11 @@ union bpf_attr {
__u32 old_prog_fd;
} link_update;
+ struct { /* struct used by BPF_ITER_CREATE command */
+ __u32 link_fd;
+ __u32 flags;
+ } iter_create;
+
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index fc1ce5ee5c3f..1f4e778d1814 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2020 Facebook */
#include <linux/fs.h>
+#include <linux/anon_inodes.h>
#include <linux/filter.h>
#include <linux/bpf.h>
@@ -19,6 +20,19 @@ struct bpf_iter_link {
struct bpf_iter_target_info *tinfo;
};
+struct extra_priv_data {
+ struct bpf_prog *prog;
+ u64 session_id;
+ u64 seq_num;
+ bool has_last;
+};
+
+struct anon_file_prog_assoc {
+ struct list_head list;
+ struct file *file;
+ struct bpf_prog *prog;
+};
+
static struct list_head targets;
static struct mutex targets_mutex;
static bool bpf_iter_inited = false;
@@ -26,6 +40,50 @@ static bool bpf_iter_inited = false;
/* protect bpf_iter_link.link->prog upddate */
static struct mutex bpf_iter_mutex;
+/* Since at anon seq_file release function, the prog cannot
+ * be retrieved since target seq_priv_size is not available.
+ * Keep a list of <anon_file, prog> mapping, so that
+ * at file release stage, the prog can be released properly.
+ */
+static struct list_head anon_iter_info;
+static struct mutex anon_iter_info_mutex;
+
+/* incremented on every opened seq_file */
+static atomic64_t session_id;
+
+static u32 get_total_priv_dsize(u32 old_size)
+{
+ return roundup(old_size, 8) + sizeof(struct extra_priv_data);
+}
+
+static void *get_extra_priv_dptr(void *old_ptr, u32 old_size)
+{
+ return old_ptr + roundup(old_size, 8);
+}
+
+static int anon_iter_release(struct inode *inode, struct file *file)
+{
+ struct anon_file_prog_assoc *finfo;
+
+ mutex_lock(&anon_iter_info_mutex);
+ list_for_each_entry(finfo, &anon_iter_info, list) {
+ if (finfo->file == file) {
+ bpf_prog_put(finfo->prog);
+ list_del(&finfo->list);
+ kfree(finfo);
+ break;
+ }
+ }
+ mutex_unlock(&anon_iter_info_mutex);
+
+ return seq_release_private(inode, file);
+}
+
+static const struct file_operations anon_bpf_iter_fops = {
+ .read = seq_read,
+ .release = anon_iter_release,
+};
+
int bpf_iter_reg_target(struct bpf_iter_reg *reg_info)
{
struct bpf_iter_target_info *tinfo;
@@ -37,6 +95,8 @@ int bpf_iter_reg_target(struct bpf_iter_reg *reg_info)
INIT_LIST_HEAD(&targets);
mutex_init(&targets_mutex);
mutex_init(&bpf_iter_mutex);
+ INIT_LIST_HEAD(&anon_iter_info);
+ mutex_init(&anon_iter_info_mutex);
bpf_iter_inited = true;
}
@@ -61,7 +121,20 @@ int bpf_iter_reg_target(struct bpf_iter_reg *reg_info)
struct bpf_prog *bpf_iter_get_prog(struct seq_file *seq, u32 priv_data_size,
u64 *session_id, u64 *seq_num, bool is_last)
{
- return NULL;
+ struct extra_priv_data *extra_data;
+
+ if (seq->file->f_op != &anon_bpf_iter_fops)
+ return NULL;
+
+ extra_data = get_extra_priv_dptr(seq->private, priv_data_size);
+ if (extra_data->has_last)
+ return NULL;
+
+ *session_id = extra_data->session_id;
+ *seq_num = extra_data->seq_num++;
+ extra_data->has_last = is_last;
+
+ return extra_data->prog;
}
int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx)
@@ -150,3 +223,90 @@ int bpf_iter_link_replace(struct bpf_link *link, struct bpf_prog *old_prog,
mutex_unlock(&bpf_iter_mutex);
return ret;
}
+
+static void init_seq_file(void *priv_data, struct bpf_iter_target_info *tinfo,
+ struct bpf_prog *prog)
+{
+ struct extra_priv_data *extra_data;
+
+ if (tinfo->target_feature & BPF_DUMP_SEQ_NET_PRIVATE)
+ set_seq_net_private((struct seq_net_private *)priv_data,
+ current->nsproxy->net_ns);
+
+ extra_data = get_extra_priv_dptr(priv_data, tinfo->seq_priv_size);
+ extra_data->session_id = atomic64_add_return(1, &session_id);
+ extra_data->prog = prog;
+ extra_data->seq_num = 0;
+ extra_data->has_last = false;
+}
+
+static int prepare_seq_file(struct file *file, struct bpf_iter_link *link)
+{
+ struct anon_file_prog_assoc *finfo;
+ struct bpf_iter_target_info *tinfo;
+ struct bpf_prog *prog;
+ u32 total_priv_dsize;
+ void *priv_data;
+
+ finfo = kmalloc(sizeof(*finfo), GFP_USER | __GFP_NOWARN);
+ if (!finfo)
+ return -ENOMEM;
+
+ mutex_lock(&bpf_iter_mutex);
+ prog = link->link.prog;
+ bpf_prog_inc(prog);
+ mutex_unlock(&bpf_iter_mutex);
+
+ tinfo = link->tinfo;
+ total_priv_dsize = get_total_priv_dsize(tinfo->seq_priv_size);
+ priv_data = __seq_open_private(file, tinfo->seq_ops, total_priv_dsize);
+ if (!priv_data) {
+ bpf_prog_sub(prog, 1);
+ kfree(finfo);
+ return -ENOMEM;
+ }
+
+ init_seq_file(priv_data, tinfo, prog);
+
+ finfo->file = file;
+ finfo->prog = prog;
+
+ mutex_lock(&anon_iter_info_mutex);
+ list_add(&finfo->list, &anon_iter_info);
+ mutex_unlock(&anon_iter_info_mutex);
+ return 0;
+}
+
+int bpf_iter_new_fd(struct bpf_link *link)
+{
+ struct file *file;
+ int err, fd;
+
+ if (link->ops != &bpf_iter_link_lops)
+ return -EINVAL;
+
+ fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fd < 0)
+ return fd;
+
+ file = anon_inode_getfile("bpf_iter", &anon_bpf_iter_fops,
+ NULL, O_CLOEXEC);
+ if (IS_ERR(file)) {
+ err = PTR_ERR(file);
+ goto free_fd;
+ }
+
+ err = prepare_seq_file(file,
+ container_of(link, struct bpf_iter_link, link));
+ if (err)
+ goto free_file;
+
+ fd_install(fd, file);
+ return fd;
+
+free_file:
+ fput(file);
+free_fd:
+ put_unused_fd(fd);
+ return err;
+}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b7af4f006f2e..458f7000887a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3696,6 +3696,30 @@ static int link_update(union bpf_attr *attr)
return ret;
}
+#define BPF_ITER_CREATE_LAST_FIELD iter_create.flags
+
+static int bpf_iter_create(union bpf_attr *attr)
+{
+ struct bpf_link *link;
+ int err;
+
+ if (CHECK_ATTR(BPF_ITER_CREATE))
+ return -EINVAL;
+
+ if (attr->iter_create.flags)
+ return -EINVAL;
+
+ link = bpf_link_get_from_fd(attr->iter_create.link_fd);
+ if (IS_ERR(link))
+ return PTR_ERR(link);
+
+ err = bpf_iter_new_fd(link);
+ if (err < 0)
+ bpf_link_put(link);
+
+ return err;
+}
+
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr;
@@ -3813,6 +3837,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_LINK_UPDATE:
err = link_update(&attr);
break;
+ case BPF_ITER_CREATE:
+ err = bpf_iter_create(&attr);
+ break;
default:
err = -EINVAL;
break;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f39b9fec37ab..576651110d16 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -113,6 +113,7 @@ enum bpf_cmd {
BPF_MAP_DELETE_BATCH,
BPF_LINK_CREATE,
BPF_LINK_UPDATE,
+ BPF_ITER_CREATE,
};
enum bpf_map_type {
@@ -590,6 +591,11 @@ union bpf_attr {
__u32 old_prog_fd;
} link_update;
+ struct { /* struct used by BPF_ITER_CREATE command */
+ __u32 link_fd;
+ __u32 flags;
+ } iter_create;
+
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF
--
2.24.1
next prev parent reply other threads:[~2020-04-27 20:13 UTC|newest]
Thread overview: 81+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-27 20:12 [PATCH bpf-next v1 00/19] bpf: implement bpf iterator for kernel data Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 01/19] net: refactor net assignment for seq_net_private structure Yonghong Song
2020-04-29 5:38 ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 02/19] bpf: implement an interface to register bpf_iter targets Yonghong Song
2020-04-28 16:20 ` Martin KaFai Lau
2020-04-28 16:50 ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 03/19] bpf: add bpf_map iterator Yonghong Song
2020-04-29 0:37 ` Martin KaFai Lau
2020-04-29 0:48 ` Alexei Starovoitov
2020-04-29 1:15 ` Yonghong Song
2020-04-29 2:44 ` Alexei Starovoitov
2020-04-29 5:09 ` Yonghong Song
2020-04-29 6:08 ` Andrii Nakryiko
2020-04-29 6:20 ` Yonghong Song
2020-04-29 6:30 ` Alexei Starovoitov
2020-04-29 6:40 ` Andrii Nakryiko
2020-04-29 6:44 ` Yonghong Song
2020-04-29 15:34 ` Alexei Starovoitov
2020-04-29 18:14 ` Yonghong Song
2020-04-29 19:19 ` Andrii Nakryiko
2020-04-29 20:15 ` Yonghong Song
2020-04-30 3:06 ` Alexei Starovoitov
2020-04-30 4:01 ` Yonghong Song
2020-04-29 6:34 ` Martin KaFai Lau
2020-04-29 6:51 ` Yonghong Song
2020-04-29 19:25 ` Andrii Nakryiko
2020-04-29 1:02 ` Yonghong Song
2020-04-29 6:04 ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 04/19] bpf: allow loading of a bpf_iter program Yonghong Song
2020-04-29 0:54 ` Martin KaFai Lau
2020-04-29 1:27 ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 05/19] bpf: support bpf tracing/iter programs for BPF_LINK_CREATE Yonghong Song
2020-04-29 1:17 ` [Potential Spoof] " Martin KaFai Lau
2020-04-29 6:25 ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 06/19] bpf: support bpf tracing/iter programs for BPF_LINK_UPDATE Yonghong Song
2020-04-29 1:32 ` Martin KaFai Lau
2020-04-29 5:04 ` Yonghong Song
2020-04-29 5:58 ` Martin KaFai Lau
2020-04-29 6:32 ` Andrii Nakryiko
2020-04-29 6:41 ` Martin KaFai Lau
2020-04-27 20:12 ` Yonghong Song [this message]
2020-04-29 5:39 ` [PATCH bpf-next v1 07/19] bpf: create anonymous bpf iterator Martin KaFai Lau
2020-04-29 6:56 ` Andrii Nakryiko
2020-04-29 7:06 ` Yonghong Song
2020-04-29 18:16 ` Andrii Nakryiko
2020-04-29 18:46 ` Martin KaFai Lau
2020-04-29 19:20 ` Yonghong Song
2020-04-29 20:50 ` Martin KaFai Lau
2020-04-29 20:54 ` Yonghong Song
2020-04-29 19:39 ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 08/19] bpf: create file " Yonghong Song
2020-04-29 20:40 ` Andrii Nakryiko
2020-04-30 18:02 ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 09/19] bpf: add PTR_TO_BTF_ID_OR_NULL support Yonghong Song
2020-04-29 20:46 ` Andrii Nakryiko
2020-04-29 20:51 ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 10/19] bpf: add netlink and ipv6_route targets Yonghong Song
2020-04-28 19:49 ` kbuild test robot
2020-04-28 19:50 ` [RFC PATCH] bpf: __bpf_iter__netlink() can be static kbuild test robot
2020-04-27 20:12 ` [PATCH bpf-next v1 11/19] bpf: add task and task/file targets Yonghong Song
2020-04-30 2:08 ` Andrii Nakryiko
2020-05-01 17:23 ` Yonghong Song
2020-05-01 19:01 ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 12/19] bpf: add bpf_seq_printf and bpf_seq_write helpers Yonghong Song
2020-04-28 6:02 ` kbuild test robot
2020-04-28 16:35 ` Yonghong Song
2020-04-30 20:06 ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 13/19] bpf: handle spilled PTR_TO_BTF_ID properly when checking stack_boundary Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 14/19] bpf: support variable length array in tracing programs Yonghong Song
2020-04-30 20:04 ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 15/19] tools/libbpf: add bpf_iter support Yonghong Song
2020-04-30 1:41 ` Andrii Nakryiko
2020-05-02 7:17 ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 16/19] tools/bpftool: add bpf_iter support for bptool Yonghong Song
2020-04-28 9:27 ` Quentin Monnet
2020-04-28 17:35 ` Yonghong Song
2020-04-29 8:37 ` Quentin Monnet
2020-04-27 20:12 ` [PATCH bpf-next v1 17/19] tools/bpf: selftests: add iterator programs for ipv6_route and netlink Yonghong Song
2020-04-30 2:12 ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 18/19] tools/bpf: selftests: add iter progs for bpf_map/task/task_file Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 19/19] tools/bpf: selftests: add bpf_iter selftests Yonghong Song
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200427201242.2995160-1-yhs@fb.com \
--to=yhs@fb.com \
--cc=andriin@fb.com \
--cc=ast@fb.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=kafai@fb.com \
--cc=kernel-team@fb.com \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).